Abstract: Example embodiments of systems and methods for application verification are provided. An application may generate a cryptographic key, and encrypt the cryptographic key with a predefined public key. A server, in data communication with the application, may include a predefined private key. The application may transmit the cryptographic key to the server. The server may receive, from the application, the cryptographic key; decrypt the cryptographic key using the predefined private key; encrypt an authorization token using the decrypted key; and transmit, to the client application, the authorization token via an out-of-band channel. The application may receive, from the server, the authorization token via the out-of-band channel; and decrypt the authorization token to obtain access to one or more services associated with the server.

Abstract: Systems and methods for customizing business applications based upon user intent scores is described. A machine learning model trained to specifically predict when a user is likely to engage in a specific activity while interacting with the business application may be trained using data regarding prior interactions between a business application and a plurality of users. The machine learning model may thereafter provide a probability score for a particular user, the probability score indicating the likelihood that the user will engage in the specific activity for which the model has been trained to predict. The probability may be combined with a business value factor to produce a user intent score indicating the relative value of the user engaging in the specific activity.

Abstract: Methods and systems are described herein for a component allocation system for temporarily allocating components via resource tokens. The component allocation system may receive a request for components that match a set of user-defined criteria. The component allocation system can determine, based on the set of user-defined criteria, components that satisfy the set of user-defined criteria. Responsive to receiving a user selection of a first and second component from the determined components, the system may input component data for each of the first and second components into a machine learning model, where the machine learning model is trained to determine whether two components are interchangeable. Responsive to obtaining the indication that the first and second component are interchangeable, the system may generate a resource token indicating temporary transfer of the first and second component to a user.

Abstract: In some embodiments, user extraction of in-video text may be facilitated. In some embodiments, a video associated with a video communication session may be processed to detect moving text to which a first user is referring in the video. Based on the detection of the moving text, location information associated with the moving text may be determined. For example, the location information may indicate spatial locations of the moving text. Based on the text location information, a graphical text location indicator may be overlayed on the video (e.g., on a first portion of a user interface of a user device) where the graphical text location indicator is presented proximate the moving text. Selectable text corresponding to the moving text and an auxiliary indicator corresponding to the graphical text location indicator may be presented on a second portion of the user interface.

Abstract: In a method for securing a web browser, display instructions for displaying web content are received from a content server by a web browser operating on a client computing device. The web browser creates a document object using the display instructions and determines from the document object whether one or more of the display instructions meet font profiling criteria selected to identify attempts to profile font display characteristics of the web browser. Responsive to a determination that font profiling criteria are met, the web browser alters a character display of the document object and implements the document object for displaying the web content on the client computing device.

Abstract: In order to provide agile and dynamic portfolio management, systems and methods for underwriting and portfolio management include an ecosystem including a platform, including processing devices, communication interfaces, runtime environments, and databases, where the databases are configured to store ecosystem data, where the ecosystem data includes data associated with a plurality of systems. A service layer is in communication with the platform, the service layer including containers executed in the runtime environment and configured to implement microservices, where each of the containers include: at least one microservice and a datastore device configured to store domain-specific data. An orchestrator is in communication with the service layer, the orchestrator to schedule execution of the microservices according to bounded contexts coordinated with composite application programming interfaces (API) interfacing with a microservice specific API.

Abstract: In some implementations, a device may receive information indicating that an instrument has been provided by a user to a recipient. The instrument may be associated with a value, and the instrument may be designated for the recipient. The device may determine, using the machine learning model, a prediction of a time of an event associated with the instrument based on the recipient. The event associated with the instrument may result in a reduction of a balance of an account of the user. The device may transmit to another device of the user, a notification indicating the prediction of the time of the event associated with the instrument.

Abstract: Systems and methods are described for maintaining bifurcated data management while labeling data for artificial intelligence model development. For example, the system may receive a first label for a first sample from a first dataset, wherein the first dataset is accessible to a first subset of a plurality of users, and wherein the first subset comprises a first attribute. The system may receive first version metadata of the first label, wherein the first version metadata comprises a proposed label for the first sample assigned by a first user. The system may determine, based on a first user input from the first user, a first grouping of source code files for storing the first version metadata, wherein the first grouping of source code files is accessible to a second subset of the plurality of users, and wherein the second subset comprises a second attribute.

Abstract: Methods and systems are described for verifying an identity of a user through contextual knowledge-based authentication. The system described uses contextual knowledge-based authentication. By verifying an identity of a user through contextual knowledge-based authentication, the verification is both more secure and more intuitive to the user. For example, by relying on confidential and/or proprietary information, the system may generate verification questions, the answers to which are known only by the user.

Abstract: Disclosed herein are system, method, and computer program product embodiments for remote activation of an automated teller machine (ATM) to dispense cash to a customer. The customer may stage a transaction using a mobile application on a mobile device. Upon the staged transaction being authenticated and approved, the customer may visit the ATM. The customer may capture an image being displayed on a display of the ATM using a camera of the mobile device. The captured image may be sent to an application server from the mobile device. The application server may associate the ATM with the staged transaction that is staged using the mobile application, and send instructions to the ATM to dispense cash according to the staged transaction.

Abstract: Systems and methods are disclosed herein for real-time digital authorization. According to some embodiments, a method includes receiving, from a user device, user information comprising one or more categories. The method further includes transferring an amount corresponding to the user information. The method also includes obtaining, from a location sensor of the user device, location data including a global position system (GPS) location for the user device and identifying one or more entities based on a correlation between the location data and a parameter defining locations of the one or more entities. The method further includes performing a mapping operation between the one or more entities and the user information and receiving a request from an entity device. The method further includes transmitting a message to the entity device indicating an operation status.

Abstract: Methods and systems are described herein for an authentication mechanism that uses cryptographic tokens and eye-tracking data. In particular, the disclosed mechanism may receive an authentication request that includes an identifier of a cryptographic token and retrieve eye-tracking data and an image associated with the cryptographic token. The eye-tracking data may store various coordinates within the image and may be encoded for use in authentication. The disclosed mechanism may then transmit the image to a computing device (e.g., associated with a user) that is able to perform gaze detection as part of an authentication operation. In response, the disclosed mechanism may receive user gaze data collected during the authentication operation and determine whether the eye-tracking data matches the user gaze data. Based on determining that the eye-tracking data matches the user gaze data, the disclosed mechanism may transmit to the computing device an indication of successful authentication.

Abstract: Systems and methods for using hash tables generating textual prediction explanations. In some aspects, the system receives a first plurality of user profiles and a corresponding plurality of resource availability values. Each user profile includes values for a first set of features. The system processes a first machine learning model to extract an explainability vector. The first machine learning model receives as input the first set of features and outputs a resource availability value. The system, using the explainability vector, selects a subset of features having corresponding values in the explainability vector above a threshold. The system generates a set of categories based on the subset of features and a hash table including the set of categories. The hash table is indexable using a hash value generated based on values for the subset of features. The system transmits to a user system corresponding a user profile a textual prediction explanation.

Abstract: A computer-implemented method to enable self-service printing with authentication includes receiving, by a server, a print-request to print a document associated with an account, the print-request received from a computing device. The method further includes adding, by the server, a print job for the document in a print queue associated with the account. The method further includes receiving, by the server, a second request to initiate printing the document associated with the account, the second request received from a printer. The method further includes releasing, by the server, the print queue associated with the account to cause the printer to print the document, the releasing being responsive to the second request being authenticated.

Abstract: Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process incoming call-center calls to provide communication summaries that capture effort levels of statements made during interactive communications. For a given call, the system receives a transcript as the input and generates a textual summary as the output. In order to improve a call summary and customize a summarization task to a call center domain, the technology disclosed herein may employ a classifier that predicts an effort level and attention score for individual utterances within a call transcript, ranks the attention scores and uses selected ones of the ranked utterances in the summary.

Abstract: Systems and methods for secure authentication information retrieval. In some aspects, the system receives a request for accessing authentication information for an authentication token. The system retrieves a user profile for the user comprising token identifiers for authentication tokens associated with the user and authentication information for each authentication token. The system receives an indication that a near field communication (NFC) interaction has been initiated between the user device and the authentication token. The system determines whether the authentication token is associated with the user and renders the authentication information into a graphical overlay. The system may additionally transmit the graphical overlay for displaying the authentication information over an image of the authentication token captured via an imaging sensor included in the user device.

Abstract: Methods and systems for facilitating group payment are disclosed. In one embodiment, a group payment system is configured to execute instructions to perform operations that include receiving, from a first computing device, a request to create a group payment event and, in response, providing to the first computing device a first interface associated with the group payment event. The operations further include receiving, from a second computing device, a request to join the group payment event and, in response, providing a second interface to the second computing device. The operations further include receiving, from the first and/or second computing devices, messages associated with the group payment event and modifying the first and second interfaces to display the messages. The operations further include receiving, from the first and/or second computing devices, financial contributions for the group payment event and modifying the first and second interfaces to display the financial contributions.

Abstract: The disclosed technology relates to analyzing report infrastructure health to determine based on lineage the downstream tables and reports that may be impacted by an infrastructure failure to thereby improve reporting accuracy. An exemplary report management device may extract database table names identified in SQL queries. The SQL queries and report metadata are analyzed to identify driver and required tables, respectively. The database table names are stored in a table inventory and the database table names associated with one of the driver or required tables is marked. For each of the SQL queries comprising a target table, elements and source table names are extracted for source tables of the target table and an association is stored. Lineage data is generated based on the association when the report was not executed successfully. A graphical representation of the report lineage including a failed table and associated source table(s) is then output.

Abstract: Disclosed herein are systems and methods for account status monitoring. The method can include receiving user registration information and account information corresponding to a first user account. The account information can include first user credit information. The method can include analyzing, by a machine learning rules engine, the account information and the user registration information to create a user behavior pattern associated with the first user account. The method can further include determining an anomaly in the user behavior pattern indicative of a life event. Based on the life event and the user registration information, the method can determine a second user account and corresponding account information comprising second user credit information. In response, the method can include predicting, by a convolutional neural network, an effect on the second user credit information resulting from the transfer of the first user credit information to the second user account.

Abstract: An automated system is provided for facilitating improvements to an incident resolution system. The system includes a scenario construction processor configured for establishing a system incident scenario and a machine learning model constructed using incident response information for each of a plurality of incidents. A simulation processor is configured to use the machine learning model to run simulations of the system incident scenario. Each simulation includes at least one variation of a selected critical action characteristic critical actions included in the scenario and each simulation produces a simulated incident resolution parameter. An improvement evaluation processor determines from the simulations, one or more of the at least one variation that results in a simulated incident resolution parameter meeting predetermined improvement criteria.